© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80704
    Prev
    Next
    INDEX
    Explanations

    country codes and English

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting numeric tokens and codes—i.e. sequences of digits or numbers embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     within
    -1.21
     beneath
    -1.01
     showed
    -0.95
     compréhension
    -0.94
    ៖
    -0.92
    */
    -0.88
     (“
    -0.87
     comenzado
    -0.87
     other
    -0.87
     found
    -0.87
    POSITIVE LOGITS
     EN
    1.05
    en
    1.00
     english
    0.99
    EN
    0.99
    weisen
    0.95
    )
    0.94
     државе
    0.93
     English
    0.93
    ťa
    0.91
    ♔
    0.90
    Activations Density 0.009%

    No Known Activations